Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    fashion and accessories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Benefits
    0.66
    0.66
    Online
    0.65
    Craft
    0.65
    산
    0.65
    ↵↵
    0.64
    Qu
    0.64
    D
    0.63
    Q
    0.63
    The
    0.62
    POSITIVE LOGITS
     perempuan
    0.82
     visok
    0.79
     wanita
    0.75
     bukan
    0.75
     hitam
    0.74
     kobiety
    0.74
     ukuran
    0.73
     mujer
    0.72
     tedavi
    0.71
     keinen
    0.71
    Act Density 0.060%

    No Known Activations